Orpo finetuned models
Muhammad Bin Usman
Muhammad2003
AI & ML interests
- Model Alignment (SFT / DPO / ORPO )
- Model Merging / Pruning / MoE + latest tecniques
- Instruction tuning and Preference datasets curation
- Evaluation
Recent Activity
updated
a model
4 days ago
Muhammad2003/LegalLlama-1B
published
a model
5 days ago
Muhammad2003/LegalLlama-1B
updated
a Space
5 days ago
Muhammad2003/legalLM
Organizations
spaces
1
models
22
Muhammad2003/LegalLlama-1B
Updated
Muhammad2003/Llama3-LegalLM
Updated
•
3
Muhammad2003/router-classifier
Text Classification
•
Updated
•
1
Muhammad2003/router-embedding
Sentence Similarity
•
Updated
•
8
•
1
Muhammad2003/TriMistral-7B-TIES
Text Generation
•
Updated
•
17
Muhammad2003/TriMistral-7B-SLERP
Text Generation
•
Updated
•
10
Muhammad2003/TriMistral-7B-MODELSTOCK
Text Generation
•
Updated
•
16
Muhammad2003/TriMistral-7B-DARETIES
Text Generation
•
Updated
•
9
Muhammad2003/Llama-3-8B-DPO-500
Text Generation
•
Updated
•
7
Muhammad2003/Llama-3-8B-DPO-1500
Text Generation
•
Updated
•
9
datasets
7
Muhammad2003/routing-dataset
Viewer
•
Updated
•
14.3k
•
25
Muhammad2003/OpenMed_11k_train
Viewer
•
Updated
•
11.3k
•
22
Muhammad2003/OpenMed_11k
Viewer
•
Updated
•
11.7k
•
42
Muhammad2003/GrandMed_364k
Viewer
•
Updated
•
364k
•
18
Muhammad2003/Nectar-DPO-50k
Viewer
•
Updated
•
50k
•
42
Muhammad2003/Big_Pretrain_11K
Viewer
•
Updated
•
11.7k
•
24
Muhammad2003/Toxic_PreTrain_8k
Viewer
•
Updated
•
8.41k
•
19